deep-research
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). In Phase 1 “Web Research Cascade,” the skill runs web agents (agent-browser → WebSearch/WebFetch) that read full-page fetched/selected web content, which can include outsider-authored text if the user can cause the workflow to fetch those pages.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata